@article{Bolser2008, abstract = {Abstract Background For over 30 years potentials of mean force have been used to evaluate the relative energy of protein structures. The most commonly used potentials define the energy of residue-residue interactions and are derived from the empirical analysis of the known protein structures. However, single-body residue 'environment' potentials, although widely used in protein structure analysis, have not been rigorously compared to these classical two-body residue-residue interaction potentials. Here we do not try to combine the two different types of residue interaction potential, but rather to assess their independent contribution to scoring protein structures. Results A data set of nearly three thousand monomers was used to compare pairwise residue-residue 'contact-type' propensities to single-body residue 'contact-count' propensities. Using a large and standard set of protein decoys we performed an in-depth comparison of these two types of residue interaction propensities. The scores derived from the contact-type and contact-count propensities were assessed using two different performance metrics and were compared using 90 different definitions of residue-residue contact. Our findings show that both types of score perform equally well on the task of discriminating between near-native protein decoys. However, in a statistical sense, the contact-count based scores were found to carry more information than the contact-type based scores. Conclusion Our analysis has shown that the performance of either type of score is very similar on a range of different decoys. This similarity suggests a common underlying biophysical principle for both types of residue interaction propensity. However, several features of the contact-count based propensity suggests that it should be used in preference to the contact-type based propensity. Specifically, it has been shown that contact-counts can be predicted from sequence information alone. In addition, the use of a single-body term allows for efficient alignment strategies using dynamic programming, which is useful for fold recognition, for example. These facts, combined with the relative simplicity of the contact-count propensity, suggests that contact-counts should be studied in more detail in the future.}, author = {Bolser, Dan M. and Filippis, Ioannis and Stehr, Henning and Duarte, Jose and Lappe, Michael}, doi = {10.1186/1472-6807-8-53}, journal = {BMC Structural Biology}, month = {jan}, pages = {53}, title = {Residue contact-count potentials are as effective as residue-residue contact-type potentials for ranking protein decoys}, url = {http://dx.doi.org/10.1186/1472-6807-8-53}, volume = {8}, year = {2008} } @article{Bolser2011, abstract = {Biology is generating more data than ever. As a result, there is an ever increasing number of publicly available databases that analyse, integrate and summarize the available data, providing an invaluable resource for the biological community. As this trend continues, there is a pressing need to organize, catalogue and rate these resources, so that the information they contain can be most effectively exploited. MetaBase (MB) (http://MetaDatabase.Org) is a community-curated database containing more than 2000 commonly used biological databases. Each entry is structured using templates and can carry various user comments and annotations. Entries can be searched, listed, browsed or queried. The database was created using the same MediaWiki technology that powers Wikipedia, allowing users to contribute on many different levels. The initial release of MB was derived from the content of the 2007 Nucleic Acids Research (NAR) Database Issue. Since then, approximately 100 databases have been manually collected from the literature, and users have added information for over 240 databases. MB is synchronized annually with the static Molecular Biology Database Collection provided by NAR. To date, there have been 19 significant contributors to the project; each one is listed as an author here to highlight the community aspect of the project.}, author = {Bolser, Dan M. and Chibon, Pierre-Yves and Palopoli, Nicolas and Gong, Sungsam and Jacob, Daniel and Angel, Victoria Dominguez Del and Del Angel, Victoria Dominguez and Swan, Dan and Bassi, Sebastian and González, Virginia and Suravajhala, Prashanth and Hwang, Seungwoo and Romano, Paolo and Edwards, Rob and Bishop, Bryan and Eargle, John and Shtatland, Timur and Provart, Nicholas J. and Clements, Dave and Renfro, Daniel P. and Bhak, Daeui and Bhak, Jong}, doi = {10.1093/nar/gkr1099}, journal = {Nucleic Acids Research}, month = {dec}, pages = {D1250-D1254}, title = {MetaBase--the wiki-database of biological databases}, url = {https://doi.org/10.1093/nar/gkr1099}, volume = {40}, year = {2011} } @article{Bolser2014, author = {Bolser, Dan M. and Kerhornou, Arnaud and Walts, Brandon and Kersey, Paul}, doi = {10.1093/pcp/pcu183}, journal = {Plant & Cell Physiology}, month = {nov}, pages = {e3-e3}, title = {Triticeae Resources In Ensembl Plants.}, url = {https://academic.oup.com/pcp/article-pdf/56/1/e3/11458414/pcu183.pdf}, volume = {56}, year = {2014} } @article{Brenchley2012, abstract = {Bread wheat (Triticum aestivum) is a globally important crop, accounting for 20 per cent of the calories consumed by humans. Major efforts are underway worldwide to increase wheat production by extending genetic diversity and analysing key traits, and genomic resources can accelerate progress. But so far the very large size and polyploid complexity of the bread wheat genome have been substantial barriers to genome analysis. Here we report the sequencing of its large, 17-gigabase-pair, hexaploid genome using 454 pyrosequencing, and comparison of this with the sequences of diploid ancestral and progenitor genomes. We identified between 94,000 and 96,000 genes, and assigned two-thirds to the three component genomes (A, B and D) of hexaploid wheat. High-resolution synteny maps identified many small disruptions to conserved gene order. We show that the hexaploid genome is highly dynamic, with significant loss of gene family members on polyploidization and domestication, and an abundance of gene fragments. Several classes of genes involved in energy harvesting, metabolism and growth are among expanded gene families that could be associated with crop productivity. Our analyses, coupled with the identification of extensive genetic variation, provide a resource for accelerating gene discovery and improving this major crop.}, author = {Brenchley, Rachel and Spannagl, Manuel and Pfeifer, Matthias and D'Amore, Rosalinda and Barker, Gary L. A. and D’Amore, Rosalinda and Allen, Alexandra M. and McKenzie, Neil and Kramer, Melissa and Kerhornou, Arnaud and Bolser, Dan and Kay, Suzanne and Waite, Darren and Trick, Martin and Bancroft, Ian and Gu, Yong and Huo, Naxin and Luo, Ming-Cheng and Sehgal, Sunish and Gill, Bikram S. and Kianian, Sharyar and Anderson, Olin and Kersey, Paul and Dvorak, Jan and McCombie, W. Richard and Hall, Anthony and Mayer, Klaus F. X. and Richard McCombie, W. and Edwards, Keith J. and Bevan, Michael W. and Hall, Neil and D'Amore, Linda}, doi = {10.1038/nature11650}, journal = {Nature}, month = {jan}, pages = {705-710}, title = {Analysis of the bread wheat genome using whole-genome shotgun sequencing}, url = {http://www.nature.com/nature/journal/v491/n7426/pdf/nature11650.pdf}, volume = {491}, year = {2012} } @article{Dafas P. Dafas2004, abstract = {MOTIVATION: Protein interactions provide an important context for the understanding of function. Experimental approaches have been complemented with computational ones, such as PSIMAP, which computes domain-domain interactions for all multi-domain and multi-chain proteins in the Protein Data Bank (PDB). PSIMAP has been used to determine that superfamilies occurring in many species have many interaction partners, to show examples of convergent evolution through shared interaction partners and to uncover complexes in the interaction map. To determine an interaction, the original PSIMAP algorithm checks all residue pairs of any domain pair defined by classification systems such as SCOP. The computation takes several days for the PDB. The computation of PSIMAP has two shortcomings: first, the original PSIMAP algorithm considers only interactions of residue pairs rather than atom pairs losing information for detailed analysis of contact patterns. At the atomic level the original algorithm would take months. Second, with the superlinear growth of PDB, PSIMAP is not sustainable. RESULTS: We address these two shortcomings by developing a family of new algorithms for the computation of domain-domain interactions based on the idea of bounding shapes, which are used to prune the search space. The best of the algorithms improves on the old PSIMAP algorithm by a factor of 60 on the PDB. Additionally, the algorithms allow a distributed computation, which we carry out on a farm of 80 Linux PCs. Overall, the new algorithms reduce the computation at atomic level from months to 20 min. The combination of pruning and distribution makes the new algorithm scalable and sustainable even with the superlinear growth in PDB.}, author = {Dafas P. Dafas, Panos and Bolser D. Bolser, D.-A.-N. and Park J. Park, Jong and Gomoluch, Jacek Gomoluch and Schroeder M. Schroeder, Michael}, doi = {10.1093/bioinformatics/bth106}, journal = {Bioinformatics}, month = {jan}, pages = {1486-1490}, title = {Using convex hulls to extract interaction interfaces from known structures}, url = {https://academic.oup.com/bioinformatics/article-pdf/20/10/1486/649859/bth106.pdf}, volume = {20}, year = {2004} } @article{Fox2014, author = {Fox, Samuel E. and Geniza, Matthew and Hanumappa, Mamatha and Naithani, Sushma and Sullivan, Chris and Preece, Justin and Tiwari, Vijay K. and Elser, Justin and Leonard, Jeffrey M. and Sage, Abigail and Gresham, Cathy and Kerhornou, Arnaud and Bolser, Dan and McCarthy, Fiona and Kersey, Paul and Lazo, Gerard R. and Jaiswal, Pankaj}, doi = {10.1371/journal.pone.0096855}, journal = {PLoS ONE}, month = {may}, pages = {e96855}, title = {De Novo Transcriptome Assembly and Analyses of Gene Expression during Photomorphogenesis in Diploid Wheat Triticum monococcum}, url = {http://dx.doi.org/10.1371/journal.pone.0096855}, volume = {9}, year = {2014} } @article{Gong2005, abstract = {Protein Structural Interactome map (PSIMAP) is a global interaction map that describes domain-domain and protein-protein interaction information for known Protein Data Bank structures. It calculates the Euclidean distance to determine interactions between possible pairs of structural domains in proteins. PSIbase is a database and file server for protein structural interaction information calculated by the PSIMAP algorithm. PSIbase also provides an easy-to-use protein domain assignment module, interaction navigation and visual tools. Users can retrieve possible interaction partners of their proteins of interests if a significant homology assignment is made with their query sequences. AVAILABILITY: http://psimap.org and http://psibase.kaist.ac.kr/}, author = {Gong, Sungsam and Yoon, Giseok and Jang, Insoo and Bolser, Dan and Dafas, Panos and Schroeder, Michael and Choi, Hansol and Cho, Yoobok and Han, Kyungsook and Lee, Sunghoon and Choi, Hwanho and Lappe, Michael and Holm, Liisa and Kim, Sangsoo and Oh, Donghoon and Bhak, Jonghwa}, doi = {10.1093/bioinformatics/bti366}, journal = {Bioinformatics}, month = {mar}, pages = {2541-2543}, title = {PSIbase: a database of protein structural interactome map (PSIMAP)}, url = {https://academic.oup.com/bioinformatics/article-pdf/21/10/2541/545866/bti366.pdf}, volume = {21}, year = {2005} } @article{Ison2013, abstract = {Motivation: Advancing the search, publication and integration of bioinformatics tools and resources demands consistent machine-understandable descriptions. A comprehensive ontology allowing such descriptions is therefore required.}, author = {Ison, Jon and Kalaš, Matúš and Jonassen, Inge and Bolser, Dan and Uludag, Mahmut and McWilliam, Hamish and Malone, James and Lopez, Rodrigo and Pettifer, Steve and Rice, Peter}, doi = {10.1093/bioinformatics/btt113}, journal = {Bioinformatics}, month = {mar}, pages = {1325-1332}, title = {EDAM: an ontology of bioinformatics operations, types of data and identifiers, topics and formats}, url = {https://academic.oup.com/bioinformatics/article-pdf/29/10/1325/710075/btt113.pdf}, volume = {29}, year = {2013} } @article{Jupe2012, abstract = {Abstract Background The potato genome sequence derived from the Solanum tuberosum Group Phureja clone DM1-3 516 R44 provides unparalleled insight into the genome composition and organisation of this important crop. A key class of genes that comprises the vast majority of plant resistance (R) genes contains a nucleotide-binding and leucine-rich repeat domain, and is collectively known as NB-LRRs. Results As part of an effort to accelerate the process of functional R gene isolation, we performed an amino acid motif based search of the annotated potato genome and identified 438 NB-LRR type genes among the ~39,000 potato gene models. Of the predicted genes, 77 contain an N-terminal toll/interleukin 1 receptor (TIR)-like domain, and 107 of the remaining 361 non-TIR genes contain an N-terminal coiled-coil (CC) domain. Physical map positions were established for 370 predicted NB-LRR genes across all 12 potato chromosomes. The majority of NB-LRRs are physically organised within 63 identified clusters, of which 50 are homogeneous in that they contain NB-LRRs derived from a recent common ancestor. Conclusions By establishing the phylogenetic and positional relationship of potato NB-LRRs, our analysis offers significant insight into the evolution of potato R genes. Furthermore, the data provide a blueprint for future efforts to identify and more rapidly clone functional NB-LRR genes from Solanum species. }, author = {Jupe, Florian and Pritchard, Leighton and Etherington, Graham J. and MacKenzie, Katrin and Cock, Peter Ja A. and Wright, Frank and Sharma, Sanjeev Kumar and Bolser, Dan and Bryan, Glenn J. and Jones, Jonathan Dg G. and Hein, Ingo}, doi = {10.1186/1471-2164-13-75}, journal = {BMC Genomics}, month = {jan}, title = {Identification and localisation of the NB-LRR gene family within the potato genome}, url = {http://dx.doi.org/10.1186/1471-2164-13-75}, volume = {13}, year = {2012} } @article{Kersey2013, abstract = {Ensembl Genomes (http://www.ensemblgenomes.org) is an integrating resource for genome-scale data from non-vertebrate species. The project exploits and extends technologies for genome annotation, analysis and dissemination, developed in the context of the vertebrate-focused Ensembl project, and provides a complementary set of resources for non-vertebrate species through a consistent set of programmatic and interactive interfaces. These provide access to data including reference sequence, gene models, transcriptional data, polymorphisms and comparative analysis. This article provides an update to the previous publications about the resource, with a focus on recent developments. These include the addition of important new genomes (and related data sets) including crop plants, vectors of human disease and eukaryotic pathogens. In addition, the resource has scaled up its representation of bacterial genomes, and now includes the genomes of over 9000 bacteria. Specific extensions to the web and programmatic interfaces have been developed to support users in navigating these large data sets. Looking forward, analytic tools to allow targeted selection of data for visualization and download are likely to become increasingly important in future as the number of available genomes increases within all domains of life, and some of the challenges faced in representing bacterial data are likely to become commonplace for eukaryotes in future.}, author = {Kersey, Paul Julian and Allen, James E. and Christensen, Mikkel and Davis, Paul and Falin, Lee J. and Grabmueller, Christoph and Hughes, Daniel Seth Toney and Humphrey, Jay and Kerhornou, Arnaud and Khobova, Julia and Langridge, Nicholas and McDowall, Mark D. and Maheswari, Uma and Maslen, Gareth and Nuhn, Michael and Ong, Chuang Kee and Paulini, Michael and Pedro, Helder and Toneva, Iliana and Tuli, Mary Ann and Walts, Brandon and Williams, Gareth and Wilson, Derek and Youens-Clark, Ken and Monaco, Marcela K. and Stein, Joshua and Wei, Xuehong and Ware, Doreen and Bolser, Daniel M. and Howe, Kevin Lee and Kulesha, Eugene and Lawson, Daniel and Staines, Daniel Michael}, doi = {10.1093/nar/gkt979}, journal = {Nucleic Acids Research}, month = {oct}, pages = {D546-D552}, title = {Ensembl Genomes 2013: scaling up access to genome-wide data}, url = {http://dx.doi.org/10.1093/nar/gkt979}, volume = {42}, year = {2013} } @article{Kim2004, author = {Kim, Wan K. and Bolser, Dan M. and Park, Jong H.}, doi = {10.1093/bioinformatics/bth053}, journal = {Bioinformatics}, month = {feb}, pages = {1138-1150}, title = {Large scale co-evolution analysis of Protein Structural Interlogues using the global Protein Structural Interactome Map (PSIMAP)}, url = {https://academic.oup.com/bioinformatics/article-pdf/20/7/1138/678761/bth053.pdf}, volume = {20}, year = {2004} } @article{Li2011, abstract = {Recent advances in sequencing technology have created unprecedented opportunities for biological research. However, the increasing throughput of these technologies has created many challenges for data management and analysis. As the demand for sophisticated analyses increases, the development time of software and algorithms is outpacing the speed of traditional publication. As technologies continue to be developed, methods change rapidly, making publications less relevant for users. The SEQanswers wiki (SEQwiki) is a wiki database that is actively edited and updated by the members of the SEQanswers community (http://SEQanswers.com/). The wiki provides an extensive catalogue of tools, technologies and tutorials for high-throughput sequencing (HTS), including information about HTS service providers. It has been implemented in MediaWiki with the Semantic MediaWiki and Semantic Forms extensions to collect structured data, providing powerful navigation and reporting features. Within 2 years, the community has created pages for over 500 tools, with approximately 400 literature references and 600 web links. This collaborative effort has made SEQwiki the most comprehensive database of HTS tools anywhere on the web. The wiki includes task-focused mini-reviews of commonly used tools, and a growing collection of more than 100 HTS service providers. SEQwiki is available at: http://wiki.SEQanswers.com/.}, author = {Li, Jing-Woei and Robison, Keith and Martin, Marcel and Sjödin, Andreas and Usadel, Bj and Young, Matthew and Olivares, Eric C. and Bolser, Dan M.}, doi = {10.1093/nar/gkr1058}, journal = {Nucleic Acids Research}, month = {nov}, pages = {D1313-D1317}, title = {The SEQanswers wiki: a wiki database of tools for high-throughput sequencing analysis}, url = {https://doi.org/10.1093/nar/gkr1058}, volume = {40}, year = {2011} } @article{Li2013, abstract = {Next-generation sequencing (NGS) is increasingly being adopted as the backbone of biomedical research. With the commercialization of various affordable desktop sequencers, NGS will be reached by increasing numbers of cellular and molecular biologists, necessitating community consensus on bioinformatics protocols to tackle the exponential increase in quantity of sequence data. The current resources for NGS informatics are extremely fragmented. Finding a centralized synthesis is difficult. A multitude of tools exist for NGS data analysis; however, none of these satisfies all possible uses and needs. This gap in functionality could be filled by integrating different methods in customized pipelines, an approach helped by the open-source nature of many NGS programmes. Drawing from community spirit and with the use of the Wikipedia framework, we have initiated a collaborative NGS resource: The NGS WikiBook. We have collected a sufficient amount of text to incentivize a broader community to contribute to it. Users can search, browse, edit and create new content, so as to facilitate self-learning and feedback to the community. The overall structure and style for this dynamic material is designed for the bench biologists and non-bioinformaticians. The flexibility of online material allows the readers to ignore details in a first read, yet have immediate access to the information they need. Each chapter comes with practical exercises so readers may familiarize themselves with each step. The NGS WikiBook aims to create a collective laboratory book and protocol that explains the key concepts and describes best practices in this fast-evolving field.}, author = {Li, Jing-Woei and Bolser, Dan and Giorgi, Federico Manuel and Manske, Magnus and Vyahhi, Nikolay and Usadel, Bj and Clavijo, Bernardo J. and Chan, Ting-Fung and Wong, Nathalie and Zerbino, Daniel and Schneider, Maria Victoria}, doi = {10.1093/bib/bbt045}, journal = {Briefings in Bioinformatics}, month = {jun}, pages = {548-555}, title = {The NGS WikiBook: a dynamic collaborative online training effort with long-term sustainability}, url = {http://www.ncbi.nlm.nih.gov/pmc/articles/PMC3771235}, volume = {14}, year = {2013} } @article{Monaco2013, abstract = {Gramene (http://www.gramene.org) is a curated online resource for comparative functional genomics in crops and model plant species, currently hosting 27 fully and 10 partially sequenced reference genomes in its build number 38. Its strength derives from the application of a phylogenetic framework for genome comparison and the use of ontologies to integrate structural and functional annotation data. Whole-genome alignments complemented by phylogenetic gene family trees help infer syntenic and orthologous relationships. Genetic variation data, sequences and genome mappings available for 10 species, including Arabidopsis, rice and maize, help infer putative variant effects on genes and transcripts. The pathways section also hosts 10 species-specific metabolic pathways databases developed in-house or by our collaborators using Pathway Tools software, which facilitates searches for pathway, reaction and metabolite annotations, and allows analyses of user-defined expression datasets. Recently, we released a Plant Reactome portal featuring 133 curated rice pathways. This portal will be expanded for Arabidopsis, maize and other plant species. We continue to provide genetic and QTL maps and marker datasets developed by crop researchers. The project provides a unique community platform to support scientific research in plant genomics including studies in evolution, genetics, plant breeding, molecular biology, biochemistry and systems biology.}, author = {Monaco, Marcela K. and Stein, Joshua and Naithani, Sushma and Wei, Sharon and Dharmawardhana, Palitha and Kumari, Sunita and Amarasinghe, Vindhya and Youens-Clark, Ken and Thomason, James and Preece, Justin and Pasternak, Shiran and Olson, Andrew and Jiao, Yinping and Lu, Zhenyuan and Bolser, Dan and Kerhornou, Arnaud and Staines, Dan and Walts, Brandon and Wu, Guanming and D'Eustachio, Peter and D’Eustachio, Peter and Haw, Robin and Croft, David and Kersey, Paul J. and Stein, Lincoln and Jaiswal, Pankaj and Ware, Doreen}, doi = {10.1093/nar/gkt1110}, journal = {Nucleic Acids Research}, month = {nov}, pages = {D1193-D1199}, title = {Gramene 2013: comparative plant genomics resources}, url = {http://dx.doi.org/10.1093/nar/gkt1110}, volume = {42}, year = {2013} } @article{Park2001, abstract = {A functional analysis of protein fold interaction suggested that structural fold families have gradually acquired more diverse interacting partners while maintaining central biochemical interactions and functions. This means that the protein interaction network (map) maintains its robust architecture due to the functional constraints associated with the interactions.}, author = {Park, J. and Bolser, Dan}, month = {feb}, title = {Conservation of Protein Interaction Network in Evolution}, year = {2001} } @article{Park2005, author = {Park, D. and Lee, S. and Bolser, D. and Schroeder, M. and Lappe, M. and Oh, D. and Bhak, J.}, doi = {10.1093/bioinformatics/bti512}, journal = {Bioinformatics}, month = {may}, pages = {3234-3240}, title = {Comparative interactomics analysis of protein family interaction networks using PSIMAP (protein structural interactome map)}, url = {https://academic.oup.com/bioinformatics/article-pdf/21/15/3234/6237373/bti512.pdf}, volume = {21}, year = {2005} } @article{Sharma2013, abstract = {Abstract The genome of potato, a major global food crop, was recently sequenced. The work presented here details the integration of the potato reference genome (DM) with a new sequence-tagged site marker−based linkage map and other physical and genetic maps of potato and the closely related species tomato. Primary anchoring of the DM genome assembly was accomplished by the use of a diploid segregating population, which was genotyped with several types of molecular genetic markers to construct a new ~936 cM linkage map comprising 2469 marker loci. In silico anchoring approaches used genetic and physical maps from the diploid potato genotype RH89-039-16 (RH) and tomato. This combined approach has allowed 951 superscaffolds to be ordered into pseudomolecules corresponding to the 12 potato chromosomes. These pseudomolecules represent 674 Mb (~93%) of the 723 Mb genome assembly and 37,482 (~96%) of the 39,031 predicted genes. The superscaffold order and orientation within the pseudomolecules are closely collinear with independently constructed high density linkage maps. Comparisons between marker distribution and physical location reveal regions of greater and lesser recombination, as well as regions exhibiting significant segregation distortion. The work presented here has led to a greatly improved ordering of the potato reference genome superscaffolds into chromosomal “pseudomolecules”.}, author = {Sharma, Sanjeev Kumar and Bolser, Daniel and de Boer, Jan and Sønderkær, Mads and Amoros, Walter and Carboni, Martin Federico and D'Ambrosio, Juan Martín and D’Ambrosio, Juan Martín and de la Cruz, German and Di Genova, Alex and Douches, David S. and Eguiluz, Maria and Guo, Xiao and Guzman, Frank and Hackett, Christine A. and Hamilton, John P. and Li, Guangcun and Li, Ying and Lozano, Roberto and Maass, Alejandro and Marshall, David and Martinez, Diana and McLean, Karen and Mejía, Nilo and Milne, Linda and Munive, Susan and Nagy, Istvan and Ponce, Olga and Ramirez, Manuel and Simon, Reinhard and Thomson, Susan J. and Torres, Yerisf and Waugh, Robbie and Zhang, Zhonghua and Huang, Sanwen and Visser, Richard G. F. and Bachem, Christian W. B. and Sagredo, Boris and Feingold, Sergio E. and Orjeda, Gisella and Veilleux, Richard E. and Bonierbale, Merideth and Jacobs, Jeanne M. E. and Milbourne, Dan and Martin, David Michael Alan and Bryan, Glenn J.}, doi = {10.1534/g3.113.007153}, journal = {G3}, month = {sep}, pages = {2031-2047}, title = {Construction of Reference Chromosome-Scale Pseudomolecules for Potato: Integrating the Potato Genome with Genetic and Physical Maps}, url = {http://dx.doi.org/10.1534/g3.113.007153}, volume = {3}, year = {2013} } @article{Stehr2009, author = {Stehr, Henning and Duarte, Jose and Lappe, Michael and Bhak, Jong and Bolser, Dan}, doi = {10.1038/npre.2009.3123}, journal = {Nature Precedings}, month = {apr}, title = {PDBWiki}, url = {http://doi.org/10.1038/npre.2009.3123}, year = {2009} } @article{Stehr2010, abstract = {The success of community projects such as Wikipedia has recently prompted a discussion about the applicability of such tools in the life sciences. Currently, there are several such ‘science-wikis’ that aim to collect specialist knowledge from the community into centralized resources. However, there is no consensus about how to achieve this goal. For example, it is not clear how to best integrate data from established, centralized databases with that provided by ‘community annotation’. We created PDBWiki, a scientific wiki for the community annotation of protein structures. The wiki consists of one structured page for each entry in the the Protein Data Bank (PDB) and allows the user to attach categorized comments to the entries. Additionally, each page includes a user editable list of cross-references to external resources. As in a database, it is possible to produce tabular reports and ‘structure galleries’ based on user-defined queries or lists of entries. PDBWiki runs in parallel to the PDB, separating original database content from user annotations. PDBWiki demonstrates how collaboration features can be integrated with primary data from a biological database. It can be used as a system for better understanding how to capture community knowledge in the biological sciences. For users of the PDB, PDBWiki provides a bug-tracker, discussion forum and community annotation system. To date, user participation has been modest, but is increasing. The user editable cross-references section has proven popular, with the number of linked resources more than doubling from 17 originally to 39 today.}, author = {Stehr, Henning and Duarte, Jose M. and Lappe, Michael and Bhak, Jong and Bolser, Dan M.}, doi = {10.1093/database/baq009}, journal = {Database}, month = {apr}, pages = {baq009-baq009}, title = {PDBWiki: added value through community annotation of the Protein Data Bank}, url = {https://doi.org/10.1093/database/baq009}, volume = {2010}, year = {2010} } @article{van Ham2011, abstract = {Potato (Solanum tuberosum L.) is the world's most important non-grain food crop and is central to global food security. It is clonally propagated, highly heterozygous, autotetraploid, and suffers acute inbreeding depression. Here we use a homozygous doubled-monoploid potato clone to sequence and assemble 86% of the 844-megabase genome. We predict 39,031 protein-coding genes and present evidence for at least two genome duplication events indicative of a palaeopolyploid origin. As the first genome sequence of an asterid, the potato genome reveals 2,642 genes specific to this large angiosperm clade. We also sequenced a heterozygous diploid clone and show that gene presence/absence variants and other potentially deleterious mutations occur frequently and are a likely cause of inbreeding depression. Gene family expansion, tissue-specific expression and recruitment of genes to new pathways contributed to the evolution of tuber development. The potato genome sequence provides a platform for genetic improvement of this vital crop.}, author = {van Ham, Roeland C. H. J. and Xu, Xun and del Rosario Herrera, Maria and de Boer, Jan and van Eck, Herman and te Lintel Hekkert, Bas and Pan, Shengkai and Cheng, Shifeng and Zhang, Bo and Mu, Desheng and Ni, Peixiang and Zhang, Gengyun and Yang (Principal, S. and Yang, Shuang and Li, Ruiqiang and Li (Principal, R. and Wang, Jun and Wang (Principal, J. and Orjeda, Gisella and Orjeda (Principal, G. and Guzman, Frank and Torres, Michael and Lozano, Roberto and Ponce, Olga and Martinez, Diana and De la Cruz, Germán and Chakrabarti (Principal, S. K. and Chakrabarti, S. K. and Patil, Virupaksh U. and Skryabin, Konstantin G. and Skryabin (Principal, K. G. and Kuznetsov, Boris B. and Ravin, Nikolai V. and Kolganova, Tatjana V. and Beletsky, Alexey V. and Mardanov, Andrei V. and Di Genova, Alex and Martin (Principal, D. and Bolser, Daniel M. and Martin, David M. A. and Li, Guangcun and Yang, Yu and Kuang, Hanhui and Hu, Qun and Xiong, Xingyao and Sagredo (Principal, B. and Bishop, Gerard J. and Sagredo, Boris and Zagorski (Principal, W. and Mejía, Nilo and Zagorski, Wlodzimierz and Gromadka, Robert and Gawor, Jan and Huang (Principal, S. and Szczesny, Pawel and Huang, Sanwen and Zhang, Zhonghua and Liang, Chunbo and He, Jun and Li, Ying and He, Ying and Xu, Jianfei and Zhang, Youjun and Xie, Binyan and Qu (Principal, D. and Du, Yongchen and Qu, Dongyu and Bonierbale, Merideth and Ghislain, Marc and Giuliano (Principal, G. and Herrera, Maria del Rosario and Giuliano, Giovanni and Pietrella, Marco and Perrotta, Gaetano and Facella, Paolo and O'Brien, Kimberly and Feingold (Principal, S. E. and O’Brien, Kimberly and Feingold, Sergio E. and Barreiro, Leandro E. and Massa, Gabriela A. and Diambra, Luis and Whitty, Brett R. and Vaillancourt, Brieanne and Lin, Haining and Massa, Alicia N. and Geoffroy, Michael and Robin Buell (Principal, C. and Lundback, Steven and DellaPenna, Dean and Buell, C. Robin and Sharma, Sanjeev Kumar and Marshall, David F. and Bryan (Principal, G. J. and Waugh, Robbie and Bryan, Glenn J. and Destefanis, Marialaura and Nagy, Istvan and Milbourne, Dan and Milbourne (Principal, D. and Thomson, Susan J. and Fiers, Mark and Jacobs, Jeanne M. E. and Jacobs (Principal, J. M. E. and Nielsen (Principal, K. L. and Nielsen, Kåre L. and Sønderkær, Mads and Iovene, Marina and Torres, Giovana A. and Jiang (Principal, J. and Jiang, Jiming and Veilleux, Richard E. and Bachem, Christian W. B. and Bachem (Principal, C. W. B. and De Boer, J. and Borm, Theo and Kloosterman, Bjorn and Van Eck, H. and Datema, Erwin and Hekkert, B. L. and Hekkert, Bas te Lintel and Goverse, Aska and Van Ham, R. C. H. J. and Visser, Richard G. F.}, doi = {10.1038/nature10158}, journal = {Nature}, month = {jul}, pages = {189-195}, title = {Genome sequence and analysis of the tuber crop potato}, url = {http://www.nature.com/nature/journal/v475/n7355/pdf/nature10158.pdf}, volume = {475}, year = {2011} }